Exposes MCP tools that screen untrusted text or URLs for prompt injection and verify shops, checkout/payment links, x402 endpoints, and ERC-20 tokens before an agent reads, approves, or pays.
Enables AI agents to run pre-purchase safety checks on shops, checkout and payment links, paid APIs, and x402 endpoints before paying, returning a pay, caution, or do_not_pay verdict with reasons.
Enables AI agents to scan untrusted web pages, emails, PDFs, and tool output for prompt injection across 17 languages, returning findings and cleaned text before the agent reads the content.